Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

[HER2 promotes cell migration via inhibiting the expression of E-cadherin in human mammary epithelial cells].

Xi bao yu fen zi mian yi xue za zhi = Chinese journal of cellular and molecular immunology·2017
Same author

Suppression of cucumber stachyose synthase gene (CsSTS) inhibits phloem loading and reduces low temperature stress tolerance.

Plant molecular biology·2017
Same author

Prognostic Factors for Recovery of Patients After Surgery for Thoracic Spinal Tuberculosis.

World neurosurgery·2017
Same author

NaK alloy-induced in vivo tumor ablation therapy.

Minimally invasive therapy & allied technologies : MITAT : official journal of the Society for Minimally Invasive Therapy·2017
Same author

Robust Granger Analysis in Lp Norm Space for Directed EEG Network Analysis.

IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2017
Same author

Cell Sheets of Co-cultured Endothelial Progenitor Cells and Mesenchymal Stromal Cells Promote Osseointegration in Irradiated Rat Bone.

Scientific reports·2017

Related Experiment Video

Updated: Jun 9, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K

SeBIR: Semantic-guided burst image restoration.

Huan Liu1, Mingwen Shao1, Yecong Wan1

  • 1School of Computer Science and Technology, China University of Petroleum (East China), Qingdao 266580, China.

Neural Networks : the Official Journal of the International Neural Network Society
|October 31, 2024
PubMed
Summary

This study introduces SeBIR, a semantic-guided model for burst image restoration. It improves alignment and fusion using Segment Anything Model (SAM) to reduce artifacts and enhance details in low-quality images.

Keywords:
Burst image restorationJoint alignment strategySegment anythingSemantic-guided fusion

More Related Videos

Measuring the Shape and Size of Activated Sludge Particles Immobilized in Agar with an Open Source Software Pipeline
09:27

Measuring the Shape and Size of Activated Sludge Particles Immobilized in Agar with an Open Source Software Pipeline

Published on: January 30, 2019

7.1K
A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment
10:39

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

2.3K

Related Experiment Videos

Last Updated: Jun 9, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K
Measuring the Shape and Size of Activated Sludge Particles Immobilized in Agar with an Open Source Software Pipeline
09:27

Measuring the Shape and Size of Activated Sludge Particles Immobilized in Agar with an Open Source Software Pipeline

Published on: January 30, 2019

7.1K
A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment
10:39

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

2.3K

Area of Science:

  • Computer Vision
  • Image Processing
  • Artificial Intelligence

Background:

  • Burst image restoration recovers details from multiple low-quality snapshots.
  • Existing methods struggle with inter-frame misalignments and varying degradations, causing artifacts.
  • Adaptive recovery considering multi-frame spatio-temporal degradation is needed.

Purpose of the Study:

  • To propose a general semantic-guided model (SeBIR) for burst image restoration.
  • To leverage semantic prior knowledge from Segment Anything Model (SAM) for adaptive recovery.
  • To address limitations of existing methods in handling inter-frame misalignments and spatio-temporal varying degradation.

Main Methods:

  • Developed a joint implicit and explicit strategy for inter-frame alignment using semantic knowledge.
  • Elaborated a semantic-guided fusion module utilizing SAM's intermediate features for adaptive feature modulation.
  • Designed a semantic-guided local loss to enhance local consistency and image quality.

Main Results:

  • SeBIR effectively achieves inter-frame alignment using semantic guidance.
  • The semantic-guided fusion module adaptively modulates features, weakening degradation and strengthening complementary information.
  • Extensive experiments demonstrate superior quantitative and qualitative performance on various burst image restoration tasks.

Conclusions:

  • SeBIR offers a novel semantic-guided approach for robust burst image restoration.
  • The integration of SAM's semantic prior knowledge enables adaptive recovery, outperforming existing methods.
  • The proposed method shows significant improvements in burst super-resolution, denoising, and low-light enhancement.